Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    discover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     raster
    -0.07
     urgency
    -0.07
     gut
    -0.07
     theater
    -0.07
    _f
    -0.06
    _lens
    -0.06
    _np
    -0.06
    %x
    -0.06
    _cod
    -0.06
    .Nodes
    -0.06
    POSITIVE LOGITS
     discovery
    0.11
     discovered
    0.10
     discover
    0.09
     discovering
    0.09
     Discovery
    0.08
    Discover
    0.08
     Discover
    0.08
    discover
    0.08
    Discovery
    0.07
     Independence
    0.07
    Act Density 0.018%

    No Known Activations